SPIE Medical Imaging 2021

Our QIAL papers presented at the SPIE Medical Imaging 2021:

  1. Clark DP, Badea CT. A constrained Bregman framework for unsupervised convolutional denoising of multi-channel x-ray CT data. SPIE Medical Imaging. 2021; 115950J. https://doi.org/10.1117/12.2581832 
  2. Holbrook MD, Clark DP, Badea CT. Deep learning based spectral distortion correction and decomposition for photon counting CT using calibration provided by an energy integrated detector. SPIE Medical Imaging. 2021; 1159520. https://doi.org/10.1117/12.2581124
  3. Holbrook MD, Clark DP, Patel R, Qi Y, Mowery YM, Badea CT. Towards deep learning segmentation of lung nodules using micro-CT data. SPIE Medical Imaging. 2021; 116000I. https://doi.org/10.1117/12.2581120

Deep Learning Approaches for Spectral CT

Our keynote talk on Deep Learning Approaches in Spectral CT at the 2nd Annual Translational Imaging Conference AI and Machine Learning in Imaging.

 

Microcephaly with altered cortical layering in GIT1 deficiency revealed by quantitative neuroimaging

We combined MRI and micro-CT to show that lack of GIT1 results in skull shape abnormalities, brain atrophy, white matter and cortical layer deficiencies. Clustering of volume covariance adjacency matrices identified vulnerable brain networks.

https://www.sciencedirect.com/science/article/pii/S0730725X20304537

 

 

Image

Optimizing Diffusion Imaging Protocols for Structural Connectomics in Mouse Models of Neurological Conditions

Network approaches provide sensitive biomarkers for neurological conditions, such as Alzheimer’s disease (AD). Mouse models can help advance our understanding of underlying pathologies, by dissecting vulnerable circuits. In this work, we have examined the balance between spatial and angular resolutions and inferred suggestions for recommended future protocols. In particular, we examined a set of nodes/brain regions that are relevant for neurodegenerative conditions such as AD.

Front. Phys., 21 April 2020 | https://doi.org/10.3389/fphy.2020.00088

Dual source hybrid spectral micro-CT using an energy-integrating and a photon-counting detector

Preclinical micro-CT provides a hotbed in which to develop new imaging technologies, including spectral CT using photon counting detector (PCD) technology. Spectral imaging using PCDs promises to expand x-ray CT as a functional imaging modality, capable of molecular imaging, while maintaining CT’s role as a powerful anatomical imaging modality. However, the utility of PCDs suffers due to distorted spectral measurements, affecting the accuracy of material decomposition. We attempt to improve material decomposition accuracy using our novel hybrid dual-source micro-CT system which combines a PCD and an energy integrating detector.  doi.org/10.1088/1361-6 

Deep learning based spectral extrapolation for dual‐source, dual‐energy x‐ray computed tomography

Data completion is needed in dual‐source, dual‐energy computed tomography (CT) when physical or hardware constraints limit the field of view (FoV) covered by one of two imaging chains. Here we published a new Deep Learning approach for Spectral Extrapolation!

MRI-Based Deep Learning Segmentation and Radiomics of Sarcoma

We have created an image processing pipeline for high-throughput, reduced-bias segmentation of multiparametric tumor MRI data and radiomics analysis, to better our understanding of preclinical imaging and the insights it provides when studying new cancer therapies.

Link to our new paper

Welcome to Duke QIAL!

Our mission is to develop, optimize and apply novel CT and MRI quantitative imaging at both preclinical and clinical levels !